© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 11564
    Prev
    Next
    INDEX
    Explanations

    instances of falsehoods and deception

    oai_token-act-pair · gpt-3.5-turbo

    instances of dishonesty or lying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Switch
    -0.82
    pour
    -0.77
    Interstitial
    -0.75
    irez
    -0.74
    jee
    -0.74
    wcs
    -0.73
    eric
    -0.73
    omer
    -0.72
     largeDownload
    -0.71
    rian
    -0.71
    POSITIVE LOGITS
     omission
    1.22
     falsely
    0.92
     innocence
    0.91
     conceal
    0.88
     incrim
    0.86
     accusation
    0.84
     accusations
    0.83
     dece
    0.81
     identities
    0.80
     witness
    0.80
    Activations Density 0.201%

    No Known Activations